Publications

Aristeidis Panos
December, 2024 In the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Decomposable Transformer Point Processes
Decomposable Transformer Point Processes
Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino, Rahaf Aljundi, Richard E. Turner
October, 2023 In the IEEE/CVF International Conference on Computer Vision
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
Aristeidis Panos, Ioannis Kosmidis, Petros Dellaportas
April, 2023 In the 26th International Conference on Artificial Intelligence and Statistics
Scalable Marked Point Processes for Exchangeable and Non-Exchangeable Event Sequences
Scalable Marked Point Processes for Exchangeable and Non-Exchangeable Event Sequences
Constantinos Daskalakis, Petros Dellaportas, Aristeidis Panos
February, 2022 In 36th AAAI Conference on Artificial Intelligence (oral)
How Good are Low-Rank Approximations in Gaussian Process Regression?
How Good are Low-Rank Approximations in Gaussian Process Regression?
Aristeidis Panos, Ioannis Kosmidis, Petros Dellaportas
May, 2021 In arXiv preprint
Scalable and Interpretable Marked Point Processes
Scalable and Interpretable Marked Point Processes
Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias
April, 2021 In Machine Learning Journal
Large Scale Multi-Label Learning using Gaussian Processes
Large Scale Multi-Label Learning using Gaussian Processes
Sebastian Bobadilla-Suarez, Christiane Ahlheim, Abhinav Mehrotra, Aristeidis Panos, Bradley C. Love
December, 2019 In Computational Brain & Behavior Journal
Measures of Neural Similarity
Measures of Neural Similarity
Aristeidis Panos
August, 2019 In Ph.D. thesis
Extreme multi-label learning with Gaussian processes
Extreme multi-label learning with Gaussian processes
Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias
July, 2018 In arXiv preprint
Fully Scalable Gaussian Processes using Subspace Inducing Inputs
Fully Scalable Gaussian Processes using Subspace Inducing Inputs